Senior AI Engineer

Jobtailor; France; Sur place; EUR 75 000 - 110 000; Plein temps

Résumé du poste

Jobtailor is seeking an AI/ML engineer to design and ship on-device models for gaming, biosensing, and peripherals. You will implement production-grade inference with tight latency and resource budgets, and write efficient C++ for runtime and SDK layers.

Work across platforms with ML frameworks like PyTorch and TensorRT, optimize models via quantization/pruning, and collaborate with platform, haptics, and audio teams to expose AI capabilities to game studios.

Qualifications

• 3+ years in AI/ML engineering or related roles.
• Proficient in C++ with real-time or systems programming.
• Experience deploying ML models on-device/edge.
• Familiarity with ML frameworks and runtimes (e.g. PyTorch, ONNX Runtime, TensorRT).
• Understanding model optimization techniques (quantization, pruning, distillation) and the trade-offs.

Responsabilités

• Design and ship local on-device AI models for gaming, biosensing, and peripherals.
• Bridge ML and real-time systems to production-grade inference with tight latency budgets.
• Implement and optimize AI/ML models for on-device inference in latency-sensitive contexts.
• Process biosignal and sensor data in real time.
• Optimize models for performance and footprint (quantization, pruning, acceleration).
• Write efficient production-quality C++ for runtime and inference layers of the SDK.
• Collaborate with platform, haptics, and audio teams to expose AI capabilities via APIs.
• Profile, benchmark, and improve inference speed, memory use, and energy efficiency.

Connaissances

C++ proficiency

Real-time/systems

Edge AI deployment

Outils

PyTorch

ONNX Runtime

TensorRT

llama.cpp / GGML

Description du poste

Responsibilities

• Design and ship local (on-device) AI models that run efficiently across gaming, biosensing, and peripheral applications.
• Work at the intersection of machine learning and real-time systems — taking models from prototype to optimized, production-grade inference that runs on the player's machine and our hardware, with tight latency and resource budgets.
• Implement and optimize AI/ML models for on-device inference in latency-sensitive gaming and peripheral contexts.
• Build and integrate models that process biosignal and sensor data (e.g. from peripherals and wearables) in real time.
• Optimize models for performance and footprint — quantization, pruning, and acceleration across CPU/GPU/NPU targets.
• Write efficient, production-quality C++ for the runtime and inference layers of our SDK.
• Collaborate with platform, haptics, and audio teams to expose AI capabilities to game studios through clean, well-documented APIs.
• Profile, benchmark, and continuously improve inference speed, memory use, and energy efficiency.

Qualifications

• 3+ years of experience in AI/ML engineering, applied ML, or a closely related role.
• Proficiency in C++ (required) — comfortable writing performant, maintainable code in a real-time or systems context.
• Hands-on experience deploying machine learning models, ideally on-device / edge rather than purely cloud.
• Familiarity with ML frameworks and runtimes (e.g. PyTorch, ONNX Runtime, TensorRT, llama.cpp / GGML, or similar).
• Understanding of model optimization techniques (quantization, pruning, distillation) and the trade-offs they involve.
• Strong fundamentals in performance profiling and working within constrained compute/latency budgets.